PREVIEW · the site is new and still changing
Nerdict
GPT-6 Lunamediumin Codex CLIAstronomical clock
Score14/14all 14 checks passed
Cost$0.005
Time1m17s
Runs of this setup#1 14/14#2 14/14#3 14/14
Astronomical clock by GPT-6 LunaOpen it running ↗

This is the exact file the model wrote, unedited, served from an isolated domain with the network blocked, as in the test.

What the robot did

The comparison clip (the same script for every model)

Checks

14/14

Written from the prompt (test v1, checks v1). The model never saw them.

  • ✓Opens without a page error
  • ✓Test hooks present (clock face, three hands, getState)
  • ✓Hands show the right time (Oct 9, 14:37:21, New York)hour 78.7° (esperado 78.7°) · minute 224.1° (esperado 224.1°) · second 126.0° (esperado 126.0°)
  • ✓Reported time is righttime=14:37:21 (esperado 14:37:21)
  • ✓Sunrise and sunset in New York (±4 min)nascer 07:00 (ref. 07:01) · pôr 18:24 (ref. 18:25)
  • ✓Moon phase and illumination (±4 points)0.008 'new moon' (ref. 0.009, aceita ['new moon', 'waning crescent'])
  • ✓After 61 s, the hands moved correctlyhour 79.2° (esperado 79.2°) · minute 230.2° (esperado 230.2°) · second 132.0° (esperado 132.0°)
  • ✓Second date (Dec 21): handshour 243.1° (esperado 243.1°) · minute 37.0° (esperado 37.0°) · second 60.0° (esperado 60.0°)
  • ✓Second date: reported timetime=08:06:10 (esperado 08:06:10)
  • ✓Second date: sunrise and sunsetnascer 07:16 (ref. 07:17) · pôr 16:31 (ref. 16:32)
  • ✓Second date: moon0.911 'waxing gibbous' (ref. 0.908, aceita ['waxing gibbous'])
  • ✓No uncaught exception during the session
  • ✓No console errors
  • ✓No network attempts
Model
GPT-6 Luna gpt-6-luna
Reasoning effort
medium
Started
Oct 9, 18:12 UTC
Harness
Codex CLI 0.162.0, by OpenAI (not ours) · one shot · tools used: 0
Harness settings
isolated container with no global instructions, read-only sandbox; shell, browser, apps, multi-agent and web off; empty /work folder · imagem=nerdict-bancada-codex:0.162.0 · sandbox=read-only
Tokens
in 6,640 · cache read 11,776 · out 9,249 · reasoning 1,722 · requests 1
Cost
$0.005 API-equivalent · extra spend $0 (subscription)
Test
Astronomical clock v1 · checks v1 · prompt ea841e16fa5c
Output file
21.7 KB · sha256 e9a8e805e40e
Run id
20261009T181258Z_relogio-v1_luna-medium_r3